Publication Type
Conference Proceeding Article
Version
publishedVersion
Publication Date
2-2023
Abstract
Current math word problem (MWP) solvers are usually Seq2Seq models trained by the (one-problem; one-solution) pairs, each of which is made of a problem description and a solution showing reasoning flow to get the correct answer. However, one MWP problem naturally has multiple solution equations. The training of an MWP solver with (one-problem; one-solution) pairs excludes other correct solutions, and thus limits the generalizability of the MWP solver. One feasible solution to this limitation is to augment multiple solutions to a given problem. However, it is difficult to collect diverse and accurate augment solutions through human efforts. In this paper, we design a new training framework for an MWP solver by introducing a solution buffer and a solution discriminator. The buffer includes solutions generated by an MWP solver to encourage the training data diversity. The discriminator controls the quality of buffered solutions to participate in training. Our framework is flexibly applicable to a wide setting of fully, semi-weakly and weakly supervised training for all Seq2Seq MWP solvers. We conduct extensive experiments on a benchmark dataset Math23k and a new dataset named Weak12k, and show that our framework improves the performance of various MWP solvers under different settings by generating correct and diverse solutions.
Keywords
Question Answering, multiple solution equations, Argumentation, problem description, training framework
Discipline
Artificial Intelligence and Robotics | Mathematics | Theory and Algorithms
Publication
Proceedings of the 37th AAAI Conference on Artificial Intelligence, AAAI 2023, Washington, February 7-14
Volume
37
First Page
13183
Last Page
13191
ISBN
9781577358800
Identifier
10.1609/aaai.v37i11.26548
Publisher
AAAI Press
City or Country
Washington
Citation
LIANG, Zhenwen; ZHANG, Jipeng; WANG, Lei; WANG, Yan; SHAO, Jie; and ZHANG, Xiangliang.
Generalizing math word problem solvers via solution diversification. (2023). Proceedings of the 37th AAAI Conference on Artificial Intelligence, AAAI 2023, Washington, February 7-14. 37, 13183-13191.
Available at: https://ink.library.smu.edu.sg/sis_research/8089
Creative Commons License
This work is licensed under a Creative Commons Attribution-NonCommercial-No Derivative Works 4.0 International License.
Additional URL
https://doi.org/10.1609/aaai.v37i11.26548
Included in
Artificial Intelligence and Robotics Commons, Mathematics Commons, Theory and Algorithms Commons